用双向映射和双分支重建提升工业缺陷检测的精度与鲁棒性
Cross-Modal Mapping and Dual-Branch Reconstruction for 2D-3D Multimodal Industrial Anomaly Detection
- 通过2D与3D双向映射建模外观-几何一致性
- 在MVTec 3D-AD上达97.3%图像级和99.6%像素级AUROC
- 无需记忆库，适用于缺图或纹理弱的工业场景
多模态工业异常检测通过融合RGB外观与3D表面几何信息提升性能，但现有无监督方法常依赖记忆库、教师-学生架构或脆弱的融合方案，在深度噪声大、纹理弱或模态缺失时鲁棒性不足。本文提出轻量级、模态灵活的无监督框架CMDR-IAD，支持2D+3D多模态及单模态（仅2D或仅3D）设置。该方法结合双向2D↔3D跨模态映射以建模外观-几何一致性，以及双分支重建分别捕捉正常纹理与几何结构。采用两阶段融合策略：可靠性门控映射异常识别空间一致的纹理-几何差异，置信度加权重建异常自适应平衡外观与几何偏差，实现深度稀疏或低纹理区域的稳定精准定位。在MVTec 3D-AD基准上，CMDR-IAD达到97.3%图像级AUROC（I-AUROC）、99.6%像素级AUROC（P-AUROC）和97.6% AUPRO，且无需记忆库。在真实聚氨酯切割数据集上，3D-only版本达92.6% I-AUROC与92.5% P-AUROC，验证其在实际工业条件下的有效性。
原文摘要 · Abstract (English)
Multimodal industrial anomaly detection benefits from integrating RGB appearance with 3D surface geometry, yet existing \emph{unsupervised} approaches commonly rely on memory banks, teacher-student architectures, or fragile fusion schemes, limiting robustness under noisy depth, weak texture, or missing modalities. This paper introduces \textbf{CMDR-IAD}, a lightweight and modality-flexible unsupervised framework for reliable anomaly detection in 2D+3D multimodal as well as single-modality (2D-only or 3D-only) settings. \textbf{CMDR-IAD} combines bidirectional 2D$\leftrightarrow$3D cross-modal mapping to model appearance-geometry consistency with dual-branch reconstruction that independently captures normal texture and geometric structure. A two-part fusion strategy integrates these cues: a reliability-gated mapping anomaly highlights spatially consistent texture-geometry discrepancies, while a confidence-weighted reconstruction anomaly adaptively balances appearance and geometric deviations, yielding stable and precise anomaly localization even in depth-sparse or low-texture regions. On the MVTec 3D-AD benchmark, CMDR-IAD achieves state-of-the-art performance while operating without memory banks, reaching 97.3\% image-level AUROC (I-AUROC), 99.6\% pixel-level AUROC (P-AUROC), and 97.6\% AUPRO. On a real-world polyurethane cutting dataset, the 3D-only variant attains 92.6\% I-AUROC and 92.5\% P-AUROC, demonstrating strong effectiveness under practical industrial conditions. These results highlight the framework's robustness, modality flexibility, and the effectiveness of the proposed fusion strategies for industrial visual inspection. Our source code is available at https://github.com/ECGAI-Research/CMDR-IAD/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。